Road network skeleton construction method and device, storage medium and computer program product
By dividing the Zhongyuan driving trajectory into conventional and turn trajectory, identifying and eliminating illegal turn trajectory, the problem of low map construction efficiency in the existing technology is solved, and a high-precision road network skeleton construction is achieved.
Patent Information
- Application Number
- CN202410944149.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art, the method of manually screening and processing abnormal driving data has resulted in low map construction efficiency and is unable to effectively build high-precision maps.
By obtaining the multi-source driving trajectory of the target road area, it is divided into conventional driving trajectory and turn-around driving trajectory, the road network skeleton is generated, and the illegal turning trajectory is identified and eliminated according to the lane path relationship, and the road network skeleton is updated.
No manual marking and handling of illegal turn-turn trajectories has been required, which improves map construction efficiency and achieves high-precision road network skeleton construction.
Smart Images

Figure CN118913245A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of map construction, and in particular to a road network skeleton construction method, device, storage medium and computer program product. Background Art
[0002] The realization of autonomous driving functions of smart cars is mostly based on high-precision maps. The current industry hotspot is to use crowd-source data to build lane-level high-precision maps with high freshness (fast updates and iterations).
[0003] In order to build lane-level high-precision maps for fully autonomous driving, it is necessary to establish a road-level road network skeleton that provides information about the drivable area for autonomous driving, which provides crucial information for vehicle path planning. However, in the current process of building maps based on multi-source data, manual screening and processing of abnormal driving data are usually used, resulting in low map building efficiency.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a road network skeleton construction method, device, storage medium and computer program product, aiming to solve the technical problem of low map construction efficiency caused by manual screening and processing of abnormal driving data.
[0006] To achieve the above objectives, the present application proposes a method for constructing a road network skeleton, the method comprising:
[0007] Acquire multi-source driving trajectories in a target road area, and divide the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories;
[0008] Based on the conventional driving trajectory, a road network skeleton is generated;
[0009] According to the U-turn driving trajectory and the road network skeleton, a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton is generated;
[0010] According to the lane path relationship, illegal U-turn trajectories are eliminated from the U-turn driving trajectories to obtain intersection U-turn trajectories, and the road network skeleton is updated based on the intersection U-turn trajectories.
[0011] In some embodiments, the step of dividing the multi-source driving trajectory into a regular driving trajectory and a U-turn driving trajectory includes:
[0012] Obtaining an overall trajectory angle of the multi-source driving trajectory;
[0013] The multi-source driving trajectory whose overall trajectory angle is smaller than the predetermined U-turn angle is used as the U-turn driving trajectory;
[0014] The multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle is used as a regular driving trajectory.
[0015] In some embodiments, the step of obtaining the overall trajectory angle of the multi-source driving trajectory includes:
[0016] Obtaining the starting point and the end point of the multi-source driving trajectory;
[0017] A first tangent direction of the starting point and a second tangent direction of the end point are calculated, and an angle between the first tangent direction and the second tangent direction is used as an overall trajectory angle of the multi-source driving trajectory.
[0018] In some embodiments, the step of generating a road network skeleton based on the conventional driving trajectory includes:
[0019] Dividing the conventional driving trajectory into trajectory segments, and converting each of the trajectory segments into trajectory nodes respectively;
[0020] Based on the connectivity relationship between the trajectory segments, the trajectory nodes are connected, and the trajectory nodes within the intersection range in the target road area are merged to generate an initial road network topology;
[0021] The trajectory segments within the intersection are grouped to obtain an intra-intersection topology, and the initial road network topology is updated based on the intra-intersection topology to obtain a road network skeleton.
[0022] In some embodiments, the step of dividing the conventional driving trajectory into trajectory segments and converting each of the trajectory segments into trajectory nodes includes:
[0023] Mapping the trajectory points of the conventional driving trajectory into a predetermined global grid, and dividing the trajectory points in each mesh of the predetermined global grid into at least one trajectory segment;
[0024] The cluster vertices in the trajectory segment are used as trajectory nodes of the trajectory segment.
[0025] In some embodiments, the step of generating a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton according to the U-turn driving trajectory and the road network skeleton comprises:
[0026] Obtaining each road network lane connected to the intersection in the road network skeleton;
[0027] The U-turn driving trajectory is matched with each road network lane to obtain a target lane of the U-turn driving trajectory as a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton.
[0028] In some embodiments, the step of removing illegal U-turn trajectories from the U-turn driving trajectory according to the lane path relationship to obtain the intersection U-turn trajectory includes:
[0029] According to the lane path relationship, construct an intersection adjacency matrix of the U-turn driving trajectory, wherein the rows and columns of the intersection adjacency matrix represent the respective entry lanes and the respective exit lanes in the road network lanes;
[0030] If there is no target element in the intersection adjacency matrix, the U-turn driving trajectory is determined to be an illegal U-turn trajectory, and the target element represents that the U-turn driving trajectory passes through any of the entry lanes and any of the exit lanes;
[0031] Illegal U-turn trajectories are eliminated from the U-turn driving trajectories to obtain intersection U-turn trajectories.
[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a road network skeleton construction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the road network skeleton construction method as described above.
[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the road network skeleton construction method described above are implemented.
[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the road network skeleton construction method as described above.
[0035] One or more technical solutions proposed in this application have at least the following technical effects:
[0036] The present application obtains the multi-source driving trajectories in the target road area and divides the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories. Thus, the U-turn driving trajectories that may be abnormal are preliminarily obtained. Then, based on the regular driving trajectories, a road network skeleton is generated. And according to the U-turn driving trajectory and the road network skeleton, the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton is generated; according to the lane path relationship, the lane of the U-turn driving trajectory in the intersection range can be determined, thereby identifying the illegal U-turn trajectory with abnormal trajectory. Then, the illegal U-turn trajectory is eliminated from the U-turn driving trajectory to obtain the intersection U-turn trajectory, and the road network skeleton is updated based on the intersection U-turn trajectory. Therefore, after the present application preliminarily divides the regular driving trajectory and the U-turn driving trajectory, the road network skeleton constructed by the regular driving trajectory is used to identify the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton, thereby determining whether the U-turn driving trajectory has a behavior that does not normally pass through the intersection range, thereby screening out the illegal U-turn trajectory with abnormal trajectory. Then, illegal U-turn trajectories are removed from the U-turn driving trajectories to obtain intersection U-turn trajectories, and the road network skeleton is updated based on the intersection U-turn trajectories. The application can realize the construction of the road network skeleton without the need for manual marking and processing of illegal U-turn trajectories, effectively improving the efficiency of map construction. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0039] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the method for constructing a road network skeleton of the present application;
[0040] Figure 2 A schematic diagram of an initial road network topology involved in an embodiment of the present application;
[0041] Figure 3 A partial schematic diagram of a road network skeleton involved in an embodiment of the present application;
[0042] Figure 4 A schematic diagram of a process flow provided for Embodiment 2 of the method for constructing a road network skeleton of the present application;
[0043] Figure 5A schematic diagram of a process flow provided for Embodiment 3 of the method for constructing a road network skeleton of the present application;
[0044] Figure 6 A schematic diagram of a construction scenario of an intersection adjacency matrix involved in an embodiment of the present application;
[0045] Figure 7 This is a schematic diagram of the device structure of the hardware operating environment involved in the road network skeleton construction method in the embodiment of the present application.
[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0049] The main solution of the embodiment of the present application is: obtaining multi-source driving trajectories in the target road area, and dividing the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories; generating a road network skeleton based on the regular driving trajectories; generating a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton based on the U-turn driving trajectory and the road network skeleton; according to the lane path relationship, eliminating illegal U-turn trajectories from the U-turn driving trajectory to obtain intersection U-turn trajectories, and updating the road network skeleton based on the intersection U-turn trajectory.
[0050] In this embodiment, for the convenience of description, the following description is made by taking the identification of a personal computer as the execution subject.
[0051] The realization of autonomous driving functions of smart cars is mostly based on high-precision maps. The current industry hotspot is to use crowd-source data to build lane-level high-precision maps with high freshness (fast updates and iterations).
[0052] In order to build a lane-level high-precision map for fully autonomous driving, it is necessary to establish a road-level network skeleton that provides autonomous driving with information about the executable area, which provides crucial information for vehicle path planning. However, the current mainstream road-level skeleton construction method is as follows: the vehicle uploads the constructed local vector map fragments to the server cloud; the server cloud performs mathematical modeling and builds an optimization model to align many local vector background image fragments to obtain a global vector map; extracts vehicle trajectory data from the global vector map, and relies on manual screening to delete unconventional data that does not meet the algorithm input requirements, and then flows into the subsequent module to generate a global road-level network skeleton. That is, in the current process of building maps based on multi-source data, manual screening and processing of abnormal driving data are usually adopted, which leads to low map construction efficiency.
[0053] The present application provides a solution, which is to initially divide the conventional driving trajectory and the U-turn driving trajectory, and then use the road network skeleton constructed by the conventional driving trajectory to identify the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton, thereby determining whether the U-turn driving trajectory has any behavior that does not normally pass through the intersection range, thereby screening out illegal U-turn trajectories with abnormal trajectories. Then, the illegal U-turn trajectories are eliminated from the U-turn driving trajectories, the intersection U-turn trajectories are obtained, and the road network skeleton is updated based on the intersection U-turn trajectories. The present application can realize the construction of the road network skeleton without the need for manual marking and processing of illegal U-turn trajectories, which effectively improves the efficiency of map construction.
[0054] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a server, etc. The following takes a personal computer as an example to illustrate this embodiment and the following embodiments.
[0055] Based on this, the present application embodiment provides a method for constructing a road network skeleton, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the road network skeleton construction method of the present application.
[0056] In this embodiment, the road network skeleton construction method includes steps S10 to S40:
[0057] Step S10, obtaining multi-source driving trajectories in the target road area, and dividing the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories;
[0058] It should be noted that the target road area is the road area where the road network skeleton is expected to be constructed, the multi-source driving trajectory is the vehicle driving trajectory collected through many data sources (such as family cars, map collection vehicles, etc.), and the U-turn driving trajectory is the multi-source driving trajectory that meets the predetermined U-turn judgment conditions, that is, the multi-source driving trajectory with U-turn behavior. The regular driving trajectory is the driving trajectory of the multi-source driving trajectory except the U-turn driving trajectory.
[0059] In this embodiment, the multi-source driving trajectory in the target road area can be obtained from the target data source (such as the Internet of Vehicles), and then after the multi-source driving trajectory is analyzed, the U-turn driving trajectory with U-turn behavior and the multi-source driving trajectory other than the U-turn driving trajectory can be identified. Exemplarily, in this embodiment, the overall trajectory angle of the multi-source driving trajectory can be obtained; the multi-source driving trajectory whose overall trajectory angle is less than the predetermined U-turn angle is used as the U-turn driving trajectory; and the multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle is used as the regular driving trajectory. Alternatively, the driving direction of each trajectory point in the multi-source driving trajectory is traversed, and if the change value of the driving direction within a predetermined time window (such as 3s, 5s, 8s, etc.) is greater than a predetermined angle (such as 160°, 170°, 180°, etc.), the multi-source driving trajectory is determined to be a U-turn driving trajectory. If the change value of the driving direction within a predetermined time window (such as 3s, 5s, 8s, etc.) is not greater than a predetermined angle, the multi-source driving trajectory is determined to be a regular driving trajectory.
[0060] Step S20, generating a road network skeleton based on the conventional driving trajectory;
[0061] This embodiment can divide the conventional driving trajectory into various trajectory segments, and convert each of the trajectory segments into trajectory nodes respectively; based on the connectivity relationship between the trajectory segments, the trajectory nodes are connected to generate an initial road network topology; the trajectory nodes within the intersection range of the target road area are merged to obtain a road network skeleton. Alternatively, this embodiment can also extract position feature points from the conventional driving trajectory, and each position feature point represents the average position of nearby trajectory points. According to the time series information of the conventional driving trajectory, the connection relationship between the position feature points is established to obtain a primary road network, and then the road area image corresponding to the primary road network is superimposed, and the skeleton in the superimposed figure is extracted using a skeleton extraction algorithm as a road network skeleton.
[0062] In a feasible implementation, step S20 may include steps S21 to S23:
[0063] Step S21, dividing the conventional driving trajectory into trajectory segments, and converting each of the trajectory segments into trajectory nodes respectively;
[0064] Step S22, based on the connectivity relationship between the trajectory segments, the trajectory nodes are connected, and the trajectory nodes within the intersection range in the target road area are merged to generate an initial road network topology;
[0065] Step S23, grouping the trajectory segments within the intersection to obtain the topology within the intersection, and updating the initial road network topology based on the topology within the intersection to obtain a road network skeleton.
[0066] In this embodiment, see Figure 2 , Figure 2 is a schematic diagram of the initial road network topology involved in the embodiment of the present application. Figure 2 The undirected curve in the figure is divided into trajectory segments, and each trajectory segment is converted into a trajectory node (i.e. Figure 2 The solid dots 1 to 20 in the figure), the trajectory node is a node that characterizes the position of the trajectory segment, which can be a clustering vertex of each trajectory point in the trajectory segment, or an average position of each trajectory point in the trajectory segment. Exemplarily, this embodiment can map the trajectory points of the conventional driving trajectory to a predetermined global grid, and divide the trajectory points in each mesh in the predetermined global grid into at least one trajectory segment; and use the clustering vertices in the trajectory segment as the trajectory nodes of the trajectory segment. Alternatively, after the conventional driving trajectory is divided into at least one road segment according to a predetermined length, the road segment is further divided according to the lane width to obtain a trajectory segment. Then, the trajectory points in the trajectory segment are clustered, and the clustering vertices are used as the trajectory nodes corresponding to the trajectory segment.
[0067] Due to the continuity of the conventional driving trajectory, this embodiment can obtain the connectivity relationship between each of the trajectory segments. Each of the trajectory segments includes a first trajectory segment and at least one second trajectory segment. If the first trajectory segment is continuous with the second trajectory segment, and the driving time corresponding to the second trajectory segment is before the driving time corresponding to the first trajectory segment, then the second trajectory segment is determined to be the predecessor connection of the first trajectory segment; if the first trajectory segment is continuous with the second trajectory segment, and the driving time corresponding to the second trajectory segment is after the driving time corresponding to the first trajectory segment, then the second trajectory segment is determined to be the successor connection of the first trajectory segment. Therefore, this embodiment can obtain the connectivity relationship (predecessor connectivity or successor connectivity) between each of the trajectory segments based on the driving time sequence relationship and continuity relationship between each of the trajectory segments. Furthermore, this embodiment can connect the trajectory nodes based on the connectivity relationship between each of the trajectory segments, and merge the trajectory nodes within the intersection range of the target road area (after merging, Figure 24), generate the initial road network topology. Therefore, the initial road network topology of this embodiment can describe the road network structure in the target road area. However, since this embodiment merges the trajectory nodes within the intersection range of the target road area, it is also necessary to optimize the road network structure within the intersection range. This embodiment can group the trajectory segments within the intersection range according to the path relationship between each lane in the initial road network topology to obtain the topology within the intersection, and update the initial road network topology based on the topology within the intersection to obtain the road network skeleton. See Figure 3 , Figure 3 It is a partial schematic diagram of the road network skeleton involved in the embodiment of the present application. Figure 3 What is shown in FIG. 1 is the skeleton part of the intersection range in the road network skeleton. Figure 3 R1 to R8 are lanes in the road network, the arrows are path directions, and the dotted lines are lane connectivity within the intersection.
[0068] In a feasible implementation, step S21 may include steps A10 to A20:
[0069] Step A10, mapping the trajectory points of the conventional driving trajectory into a predetermined global grid, and dividing the trajectory points in each mesh of the predetermined global grid into at least one trajectory segment;
[0070] Step A20: using the cluster vertices in the trajectory segment as trajectory nodes of the trajectory segment.
[0071] It should be noted that the predetermined global grid is a grid of fixed specifications that is pre-set to cover the entire world.
[0072] In this embodiment, the trajectory points of the conventional driving trajectory are mapped to a predetermined global grid, and the trajectory points in each mesh of the predetermined global grid are divided into at least one trajectory segment. Exemplarily, in this embodiment, the trajectory points whose similarity reaches a first similarity threshold in each mesh can be clustered to obtain at least one target cluster, so as to roughly classify the target as a trajectory segment. Then, the cluster vertices in the trajectory segment can be used as the trajectory nodes of the trajectory segment to characterize the position of the trajectory segment in the predetermined global grid.
[0073] Step S30, generating a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton according to the U-turn driving trajectory and the road network skeleton;
[0074] This embodiment can match the U-turn driving trajectory with the road network skeleton, obtain the target lane of the U-turn driving trajectory passing through the intersection range in the road network skeleton, and use the target lane as the lane path relationship. Exemplarily, this embodiment can obtain each road network lane in the road network skeleton connected to the intersection range; match the U-turn driving trajectory with each road network lane, and obtain the target lane of the U-turn driving trajectory as the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton. It can be understood that the lane path information at least includes the target lane of the U-turn driving trajectory passing through the intersection range.
[0075] In some embodiments, step S30 includes steps S31-S32:
[0076] Step S31, obtaining each road network lane connected to the intersection in the road network skeleton;
[0077] Step S32, matching the U-turn driving trajectory with each road network lane to obtain the target lane of the U-turn driving trajectory as the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton.
[0078] In this embodiment, the road network lanes (such as Figure 3 R1~R8 in the road network skeleton). Then, the U-turn driving trajectory is matched with each road network lane, and the road network lane passed by the U-turn driving trajectory is used as the target lane, and then the target lane passed by the U-turn driving trajectory can be used as the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton. Thus, this embodiment can identify the target lane of the U-turn driving trajectory passing through the intersection range.
[0079] Step S40: according to the lane path relationship, remove the illegal U-turn trajectory from the U-turn driving trajectory to obtain the intersection U-turn trajectory, and update the road network skeleton based on the intersection U-turn trajectory.
[0080] Since the lane path relationship describes the target lane through which the U-turn driving trajectory passes through the intersection range, the present embodiment can identify whether there are any illegal behaviors (such as non-intersection U-turns, driving in the opposite direction at an intersection, reversing at an intersection, and other illegal driving behaviors) in the U-turn driving trajectory based on the lane path relationship. For example, if there is no target lane in the lane path relationship, or there is only an entry lane or an exit lane in the target lane, the U-turn driving trajectory can be determined to be an illegal U-turn trajectory. Therefore, the present embodiment removes the illegal U-turn trajectory from the U-turn driving trajectory, obtains the intersection U-turn trajectory, and updates the road network skeleton based on the intersection U-turn trajectory. The present embodiment can obtain the U-turn connectivity relationship within the intersection range based on the intersection U-turn trajectory, and connects the road network lanes within the intersection range in the road network skeleton based on the U-turn connectivity relationship (such as Figure 3 The dotted line between R5 and R6 in FIG. 1 is used to update the road network skeleton.
[0081] This embodiment provides a method for constructing a road network skeleton, which obtains multi-source driving trajectories in a target road area and divides the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories. Thus, a U-turn driving trajectory that may be abnormal is preliminarily obtained. Then, based on the regular driving trajectory, a road network skeleton is generated. And according to the U-turn driving trajectory and the road network skeleton, a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton is generated; according to the lane path relationship, the lane through which the U-turn driving trajectory passes in the intersection range can be determined, thereby identifying an illegal U-turn trajectory with an abnormal trajectory. Then, the illegal U-turn trajectory is removed from the U-turn driving trajectory to obtain an intersection U-turn trajectory, and the road network skeleton is updated based on the intersection U-turn trajectory. Thus, after preliminarily dividing the regular driving trajectory and the U-turn driving trajectory, this embodiment identifies the lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton with the help of the road network skeleton constructed by the regular driving trajectory, thereby determining whether the U-turn driving trajectory has a behavior that does not normally pass through the intersection range, thereby screening out illegal U-turn trajectories with abnormal trajectories. Then, illegal U-turn trajectories are removed from the U-turn driving trajectories to obtain intersection U-turn trajectories, and the road network skeleton is updated based on the intersection U-turn trajectories. This embodiment can realize the construction of the road network skeleton without manually marking and processing illegal U-turn trajectories, effectively improving the efficiency of map construction.
[0082] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 The step of dividing the multi-source driving trajectory into a regular driving trajectory and a U-turn driving trajectory in step S10 includes steps S11 to S13:
[0083] Step S11, obtaining the overall trajectory angle of the multi-source driving trajectory;
[0084] Step S12, taking the multi-source driving trajectory whose overall trajectory angle is smaller than the predetermined U-turn angle as the U-turn driving trajectory;
[0085] Step S13: taking the multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle as a regular driving trajectory.
[0086] It should be noted that the overall trajectory angle is the angle of the multi-source driving trajectory as a whole.
[0087] In this embodiment, the starting point and the end point of the multi-source driving trajectory can be obtained, and then the first tangent direction of the starting point and the second tangent direction of the end point can be calculated, and the angle between the first tangent direction and the second tangent direction can be used as the overall trajectory angle of the multi-source driving trajectory. Alternatively, the angle between the initial vector and the final vector of the multi-source driving trajectory can be calculated as the overall trajectory angle of the multi-source driving trajectory. In this embodiment, it can also be determined by the straight line between the starting point and the end point of the multi-source driving trajectory, for example, by using the straight line between the starting point and the end point of the multi-source driving trajectory to find the farthest trajectory point on the multi-source driving trajectory that is farthest from the straight line, and the angle formed by the farthest trajectory point as the vertex and the starting point and the end point as the end points is used as the overall trajectory angle. Then, the multi-source driving trajectory whose overall trajectory angle is less than the predetermined U-turn angle can be used as a U-turn driving trajectory. The multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle is used as a regular driving trajectory. Therefore, this embodiment can quickly divide the multi-source driving trajectory by the overall trajectory angle of the multi-source driving trajectory, and obtain a U-turn driving trajectory with a U-turn behavior and a regular driving trajectory without a U-turn behavior.
[0088] In some embodiments, step S11 includes steps B10 to B20:
[0089] Step B10, obtaining the starting point and the end point of the multi-source driving trajectory;
[0090] Step B20, calculating a first tangent direction of the starting point and a second tangent direction of the end point, and taking the angle between the first tangent direction and the second tangent direction as the overall trajectory angle of the multi-source driving trajectory.
[0091] In this embodiment, since the multi-source driving trajectory is a vehicle driving trajectory, the trajectory structure of the vehicle driving trajectory is usually simpler than that of personnel activity trajectories, drone flight trajectories, etc. Therefore, this embodiment can obtain the starting point and the end point of the multi-source driving trajectory; calculate the first tangent direction of the starting point and the second tangent direction of the end point, and use the angle between the first tangent direction and the second tangent direction as the overall trajectory angle of the multi-source driving trajectory. This embodiment uses the angle between the tangent directions of the starting point and the end point of the multi-source driving trajectory as the overall trajectory angle, which effectively improves the recognition efficiency of the overall trajectory angle of the multi-source driving trajectory.
[0092] In the second embodiment of the present application, the overall trajectory angle of the multi-source driving trajectory is obtained; the multi-source driving trajectory whose overall trajectory angle is less than the predetermined U-turn angle is used as the U-turn driving trajectory; and the multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle is used as the regular driving trajectory. This embodiment quickly realizes the division between the U-turn driving trajectory and the regular driving trajectory by the overall trajectory angle of the multi-source driving trajectory.
[0093] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , step S40 includes steps S41 to S43:
[0094] Step S41, constructing an intersection adjacency matrix of the U-turn driving trajectory according to the lane path relationship, wherein the rows and columns of the intersection adjacency matrix represent the respective entry lanes and the respective exit lanes in the road network lanes;
[0095] Step S42: if there is no target element in the intersection adjacency matrix, then the U-turn driving trajectory is determined to be an illegal U-turn trajectory, and the target element represents that the U-turn driving trajectory passes through any of the entry lanes and any of the exit lanes;
[0096] Step S43, eliminating illegal U-turn trajectories from the U-turn driving trajectories to obtain intersection U-turn trajectories.
[0097] It should be noted that the entry lane is the road network lane entering the intersection, and the exit lane is the road network lane exiting the intersection. The rows and columns of the intersection adjacency matrix are the entry lanes in the road network lanes (such as Figure 3 The road network lanes R2, R4, R6, R8) and the exit lanes (such as Figure 3For example, in this embodiment, the rows of the intersection adjacency matrix are the entry lanes in the road network lanes, and the columns of the intersection adjacency matrix are the exit lanes in the road network lanes; or the rows of the intersection adjacency matrix are the exit lanes in the road network lanes, and the columns of the intersection adjacency matrix are the entry lanes in the road network lanes.
[0098] See also Figure 6 , Figure 6 A schematic diagram of a construction scenario of an intersection adjacency matrix involved in an embodiment of the present application. Figure 6 The left image in the middle represents the lane path relationship, and the lane path relationship includes the target lanes (R5 and R6). Then, the target element (i.e. Figure 6 ), and obtain the intersection adjacency matrix of the U-turn driving trajectory. The rows and columns of the predetermined adjacency matrix respectively represent the entry lanes and exit lanes in the road network lanes. Then, the intersection adjacency matrix of the U-turn driving trajectory is identified. If there is no target element in the intersection adjacency matrix, it means that the U-turn driving trajectory does not pass through the intersection range normally (i.e., it enters from any of the entry lanes and exits from any of the exit lanes). There may be illegal driving behaviors such as non-intersection U-turns, reverse driving at intersections, and reversing at intersections. In this case, the U-turn driving trajectory can be determined as an illegal U-turn trajectory, and the target element represents that the U-turn driving trajectory passes through any of the entry lanes and any of the exit lanes. Then, the illegal U-turn trajectory is eliminated from the U-turn driving trajectory to obtain the intersection U-turn trajectory.
[0099] This embodiment describes the lane path relationship in the form of an adjacency matrix, which is conducive to simplifying the identification process of the illegal U-turn trajectory in the U-turn driving trajectory and improving the identification efficiency.
[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the road network skeleton construction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0101] The present application provides a road network skeleton construction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the road network skeleton construction method in the above-mentioned embodiment one.
[0102] Reference below Figure 7, which shows a schematic diagram of the structure of a road network skeleton construction device suitable for implementing the embodiment of the present application. The road network skeleton construction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The road network skeleton construction device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0103] like Figure 7 As shown, the road network skeleton construction device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the road network skeleton construction device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the road network skeleton construction device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a road network skeleton construction device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0104] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0105] The road network skeleton construction device provided by the present application adopts the road network skeleton construction method in the above embodiment, which can solve the technical problem that the efficiency of map construction is low due to the manual screening and processing of abnormal driving data. Compared with the prior art, the beneficial effects of the road network skeleton construction device provided by the present application are the same as the beneficial effects of the road network skeleton construction method provided by the above embodiment, and the other technical features of the road network skeleton construction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0106] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0108] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the road network skeleton construction method in the above-mentioned embodiment.
[0109] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0110] The above-mentioned computer-readable storage medium may be included in the road network skeleton construction device; or it may exist independently without being assembled into the road network skeleton construction device.
[0111] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the road network skeleton construction device, the road network skeleton construction device is enabled to: obtain multi-source driving trajectories in the target road area, and divide the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories; generate a road network skeleton based on the regular driving trajectories; generate a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton according to the U-turn driving trajectory and the road network skeleton; according to the lane path relationship, eliminate illegal U-turn trajectories from the U-turn driving trajectory to obtain intersection U-turn trajectories, and update the road network skeleton based on the intersection U-turn trajectory.
[0112] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0113] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0114] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0115] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned road network skeleton construction method, and can solve the technical problem of low map construction efficiency caused by the manual screening and processing of abnormal driving data. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the road network skeleton construction method provided in the above-mentioned embodiment, and will not be repeated here.
[0116] The present application also provides a computer program product, including a computer program, which implements the steps of the road network skeleton construction method as described above when executed by a processor.
[0117] The computer program product provided by the present application can solve the technical problem that the efficiency of map construction is low due to the manual screening and processing of abnormal driving data. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the road network skeleton construction method provided by the above embodiment, and will not be elaborated here.
[0118] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A road network skeleton construction method, It is characterized in that The road network skeleton construction method comprises: Acquire multi-source driving trajectories in a target road area, and divide the multi-source driving trajectories into regular driving trajectories and U-turn driving trajectories; Based on the conventional driving trajectory, a road network skeleton is generated; According to the U-turn driving trajectory and the road network skeleton, a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton is generated; According to the lane path relationship, illegal U-turn trajectories are eliminated from the U-turn driving trajectories to obtain intersection U-turn trajectories, and the road network skeleton is updated based on the intersection U-turn trajectories.
2. The method according to claim 1, It is characterized in that The step of dividing the multi-source driving trajectory into a conventional driving trajectory and a U-turn driving trajectory comprises: Obtaining an overall trajectory angle of the multi-source driving trajectory; The multi-source driving trajectory whose overall trajectory angle is smaller than the predetermined U-turn angle is used as the U-turn driving trajectory; The multi-source driving trajectory whose overall trajectory angle is not less than the predetermined U-turn angle is used as a regular driving trajectory.
3. The method according to claim 2, It is characterized in that The step of obtaining the overall trajectory angle of the multi-source driving trajectory comprises: Obtaining the starting point and the end point of the multi-source driving trajectory; A first tangent direction of the starting point and a second tangent direction of the end point are calculated, and an angle between the first tangent direction and the second tangent direction is used as an overall trajectory angle of the multi-source driving trajectory.
4. The method according to claim 1, It is characterized in that The step of generating a road network skeleton based on the conventional driving trajectory comprises: Dividing the conventional driving trajectory into trajectory segments, and converting each of the trajectory segments into trajectory nodes respectively; Based on the connectivity relationship between the trajectory segments, the trajectory nodes are connected, and the trajectory nodes within the intersection range in the target road area are merged to generate an initial road network topology; The trajectory segments within the intersection are grouped to obtain an intra-intersection topology, and the initial road network topology is updated based on the intra-intersection topology to obtain a road network skeleton.
5. The method according to claim 4, It is characterized in that The step of dividing the conventional driving trajectory into trajectory segments and converting each of the trajectory segments into trajectory nodes comprises: Mapping the trajectory points of the conventional driving trajectory into a predetermined global grid, and dividing the trajectory points in each mesh of the predetermined global grid into at least one trajectory segment; The cluster vertices in the trajectory segment are used as trajectory nodes of the trajectory segment.
6. The method according to any one of claims 1 to 5, It is characterized in that The step of generating a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton according to the U-turn driving trajectory and the road network skeleton comprises: Obtaining each road network lane connected to the intersection in the road network skeleton; The U-turn driving trajectory is matched with each road network lane to obtain a target lane of the U-turn driving trajectory as a lane path relationship between the U-turn driving trajectory and the intersection range in the road network skeleton.
7. The method according to claim 6, It is characterized in that The step of removing illegal U-turn trajectories from the U-turn driving trajectories according to the lane path relationship to obtain intersection U-turn trajectories includes: According to the lane path relationship, construct an intersection adjacency matrix of the U-turn driving trajectory, wherein the rows and columns of the intersection adjacency matrix represent the respective entry lanes and the respective exit lanes in the road network lanes; If there is no target element in the intersection adjacency matrix, the U-turn driving trajectory is determined to be an illegal U-turn trajectory, and the target element represents that the U-turn driving trajectory passes through any of the entry lanes and any of the exit lanes; Illegal U-turn trajectories are eliminated from the U-turn driving trajectories to obtain intersection U-turn trajectories.
8. A road network skeleton construction device, It is characterized in that The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the road network skeleton construction method according to any one of claims 1 to 7.
9. A storage medium, It is characterized in that The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the road network skeleton construction method according to any one of claims 1 to 7 are implemented.
10. A computer program product, It is characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the road network skeleton construction method as claimed in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Road network structure base map generation method and device, computer equipment and storage medium
CN119146998A
Phase cross-road-network migration method based on large model and intersection driving track
CN122223987A
